High-risk neuroblastoma is a very aggressive disease, with excessive tumor growth and poor outcomes. A proper stratification of the high-risk patients by prognostic outcome is important for treatment. However, there is still a lack of survival stratification for the high-risk neuroblastoma. To fill the gap, we adopt a deep learning algorithm, Autoencoder, to integrate multi-omics data, and combine it with K-means clustering to identify two subtypes with significant survival differences. By comparing the Autoencoder with PCA, iCluster, and DGscore about the classification based on multi-omics data integration, Autoencoder-based classification outperforms the alternative approaches. Furthermore, we also validated the classification in two independent datasets by training machine-learning classification models, and confirmed its robustness. Functional analysis revealed that MYCN amplification was more frequently occurred in the ultra-high-risk subtype, in accordance with the overexpression of MYC/MYCN targets in this subtype. In summary, prognostic subtypes identified by deep learning-based multi-omics integration could not only improve our understanding of molecular mechanism, but also help the clinicians make decisions.

Next-generation sequencing (NGS) is being used in clinical testing. Government authorities in both China and the United States are overseeing the clinical application of NGS instruments and reagents. In addition, the US Association for Molecular Pathology and the College of American Pathologists have jointly released a guidance to standardize the analysis and interpretation of NGS data involved in clinical testing. At present, the analysis strategies and pipelines for NGS data related to the clinical detection of pediatric disease are similar to those used for adult diseases. However, for rare pediatric diseases without linkage to known genetic variants, it is currently difficult to detect the relevant pathogenic genes using NGS technology. Additionally, it is challenging to identify novel pathogenic genes of familial pediatric tumors. Therefore, characterization of the pathogenic genes associated with above diseases is important for the diagnosis and treatment of rare diseases in children. This article introduces the general pipelines for NGS data analyses of diseases and elucidates data analysis strategies for the pathogenic genes of rare pediatric diseases and familial pediatric tumors.

Chediak-Higashi syndrome (CHS) is a rare autosomal recessive disease characterized by varying degrees of oculocutaneous albinism, recurrent infections, and a mild bleeding tendency, with late neurologic dysfunction. This syndrome is molecularly characterized by pathognomonic mutations in the LYST (lysosomal trafficking regulator). Using whole genome sequencing (WGS) we attempted to identify novel mutations of CHS based on a family of CHS with atypical symptoms. The two patients demonstrated a phenotypic constellation including partial oculocutaneous albinism, frequency upper respiratory infection or a marginal intelligence, without bleeding tendency and severe immunodeficiency. WGS revealed two compound LYST mutations including a maternally inherited chr1:235969126G > A (rs80338652) and a novel paternally inherited chr1: 235915327A > AT, associated with autosomal recessive CHS. These two variants fall in the coding regions of LYST, resulting in premature truncation of LYST due to R1104X/N2535KfsX2 induced incomplete translation. Notably, the heterozygous carriers (i.e. parents) were unaffected. Our finding also reveals decreased plasma serotonin levels in patients with CHS compared with unaffected individuals for the first time. The present study contributes to improved understanding of the causes of this disease and provides new ideas for possible treatments.Chediak-Higashi Syndrome (CHS) is a rare autosomal recessive disease, characterized by partial oculocutaneous albinism (OCA), increased susceptibility to infection, a mild bleeding tendency, and/or late-onset progressive neurological impairment 1 . Bone marrow transplantation (BMT) is an acceptable curative treatment for CHS 2 . Defective structure or function of melanosomes in melanocytes is causative of OCA in CHS 3 . Large eosinophilic,

Acute appendicitis is one of the most common acute abdomens, but the confident preoperative diagnosis is still a challenge. In order to profile noninvasive urinary biomarkers that could discriminate acute appendicitis from other acute abdomens, we carried out mass spectrometric experiments on urine samples from patients with different acute abdomens and evaluated diagnostic potential of urinary proteins with various machine-learning models. Firstly, outlier protein pools of acute appendicitis and controls were constructed using the discovery dataset (32 acute appendicitis and 41 control acute abdomens) against a reference set of 495 normal urine samples. Ten outlier proteins were then selected by feature selection algorithm and were applied in construction of machine-learning models using naïve Bayes, support vector machine, and random forest algorithms. The models were assessed in the discovery dataset by leave-one-out cross validation and were verified in the validation dataset (16 acute appendicitis and 45 control acute abdomens). Among the three models, random forest model achieved the best performance: the accuracy was 84.9% in the leave-one-out cross validation of discovery dataset and 83.6% (sensitivity: 81.2%, specificity: 84.4%) in the validation dataset. In conclusion, we developed a 10-protein diagnostic panel by the random forest model that was able to distinguish acute appendicitis from confusable acute abdomens with high specificity, which indicated the clinical application potential of noninvasive urinary markers in disease diagnosis.

Hepatoblastoma (HB), a leading primary hepatic malignancy in children, originates from primitive hepatic stem cells. This study aimed to uncover the genetic variants that are responsible for HB oncogenesis. One family, which includes the healthy parents, and two brothers affected by HB, was recruited. Whole-genome sequencing (WGS) of germline DNA from all the family members identified two maternal variants, located within APC gene and X-linked WAS gene, which were harbored by the two brothers. The mutation of APC (rs137854573, c.C1606T, p.R536X) could result in HB carcinogenesis by activating Wnt signaling. The WAS variant (c.G3T, p.M1-P5del) could promote HB cell proliferation and inhibit T-cell-based immunity by activating PLK1 signaling and inactivating TCR signaling. Further analysis reflected that WAS deficiency might affect the antitumor activity of natural killer and dendritic cells. In summary, the obtained results imply that an APC mutant together with an X-linked WAS mutant, could lead to HB tumorigenesis by activating Wnt and PLK1 signaling, inhibiting TCR signaling, and reducing the antitumor activity of natural killer and dendritic cells.